We propose a transformation of real input vectors to output binary vectors by projection
using a binary random matrix with elements {0, 1} and thresholding. We investigate the rate …

Introduction. Neural network models of autoassociative, distributed memory allow storage
and retrieval of many items (vectors) where the number of stored items can exceed the …

Criteria are developed to determine the optimal number of components of a linear model in
solving a discrete ill-posed problem by the methods of truncated singular value …

We analyze the estimation of the angle, scalar product, and the Euclidean distance of real-
valued vectors using binary vectors with controlled sparsity. Transformation is carried out by …

Averaging over matrices in solving discrete ill-posed problems on the basis of random projection
Page 1 CSIT 2017, 05 – 08 September, 2017, Lviv, Ukraine 473 Averaging over matrices in …

This article analytically studies the dependence of components of the error of reconstructing
the true signal on the number of rows of a random projection matrix. It is shown that, with …

This article proposes to use a binary random matrix with the elements {0, 1} to project input
floating-point vectors onto output floating-point vectors of smaller dimension. The accuracies …

A new radial columnar architecture for the modular assembly neural network is proposed
together with a modification of this architecture which differs in less number of learning …

To solve discrete ill-posed problems by the random projection method, the error bias and
variance that arise from averaging over the random matrix realizations are studied. An …

We propose an algorithm for finding a set of texture features characterizing the most
homogeneous texture area of an input image. The found set of features is intended for …